Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Transcription factor regulatory networks underlie major features of cellular identity and complex function such as pluripotency, development and differentiation. Li and colleagues develop a graph neural network to predict transcription factor regulatory networks based on single-cell ATAC-seq data.
Accurate prediction of complex systems such as protein folding, weather forecasting and social dynamics is a core challenge in various disciplines. By fusing machine learning algorithms and classic equation-free methodologies, it is possible to reduce the computational effort of large-scale simulations by up to two orders of magnitude while maintaining the prediction accuracy of the full system dynamics.
Multiplex immunofluorescence imaging can provide a wealth of data compared to immunohistochemical staining, which is cheaper and more widely available. Ghahremani et al. present DeepLIIF, a GAN-based cell segmentation and classification approach, which is trained on co-registered images of these two modalities to provide the insights from the more data-rich muliplex data from simpler IHC images.
Fragmentation of peptides leaves characteristic patterns in mass spectrometry data, which can be used to identify protein sequences, but this method is challenging for mutated or modified sequences for which limited information exist. Altenburg et al. use an ad hoc learning approach to learn relevant patterns directly from unannotated fragmentation spectra.
An automated workflow for scanning probe microscopy, steered by an active learning framework, can efficiently explore relationships between local domain structure and physical properties. Such a capability is demonstrated in a piezoresponse force microscopy experiment to guide measurements of ferroelectric materials.
To perform electronic structure calculations in quantum chemistry systems, methods are needed that are both accurate and scalable as the size of the molecule of interest increases. Barrett and colleagues employ an autoregressive neural-network ansatz that allows them to study larger molecules than previously attempted with neural-network quantum state approaches.
The human leukocyte antigen (HLA) complex plays an important role in building an immune response, but it is hard to predict which peptides will bind to it. Chu et al. present a transformer-based approach to identify which peptides have a high binding affinity to HLA, a task that can also be translated to other binding problems.
The spatial homogeneity of urban road networks can be quantified in a fine-grained manner with graph neural networks. This method is studied across 11,790 inner-city road networks around the world and can be used to study socioeconomic development and help with urban planning.
Large language models identify patterns in the relations between words and capture their relations in an embedding space. Schramowski and colleagues show that a direction in this space can be identified that separates ‘right’ and ‘wrong’ actions as judged by human survey participants.
Deep learning methods have in recent years shown promising results in characterizing proteins and extracting complex sequence–structure–function relationships. This Analysis describes a benchmarking study to compare the performances and advantages of recent deep learning approaches in a range of protein prediction tasks.
Knowledge of the wide array of epigenomic signals provides biological insight into the state of a give cell type, but it is infeasible to experimentally characterize all possible types of epigenomic signal in the multitude of cell types in the human body. The authors present Ocelot, a machine learning approach for imputing cell-type-specific epigenomic signals along the genome.
Quantum annealers are computational models implemented on quantum hardware that can efficiently solve combinatorial optimization problems. Annealing schedules with enhanced performance can be discovered with a Monte Carlo tree search algorithm and an enhanced version incorporating value and policy neural networks—as inspired by DeepMind’s AlphaZero.
Molecular representations are hard to design due to the large size of the chemical space, the amount of potentially important information in a molecular structure and the relatively low number of annotated molecules. Still, the quality of these representations is vital for computational models trying to predict molecular properties. Wang et al. present a contrastive learning approach to provide differentiable representations from unlabelled data.
High-throughput single-cell sequencing data can provide valuable biological insights but are computationally challenging to analyse due to the dimensionality of the data and batch-specific biases. Kopp and colleagues have developed a variational auto-encoder-based method using a novel loss function for simultaneous batch correction and dimensionality reduction.
Tropical diseases, such as malaria, can develop resistance to specific drugs. Godinez and colleagues present here a generative design approach to find new anti-malarial drugs to circumvent this resistance.
The Large Hadron Collider produces 40 million collision events per second, most of which need to be discarded by a real-time filtering system. Unsupervised deep learning algorithms are developed and deployed on custom electronics to search for rare events indicating new physics, rather than for specific events led by theory.
High-fidelity haptic sensors with three-dimensional sensing surfaces are needed to advance dexterous robotic manipulation. The authors develop a sensor design that offers accurate force sensation across a three-dimensional surface while being robust, low-cost and easy to fabricate.
The combination of object recognition and viewpoint estimation is essential for visual understanding. However, convolutional neural networks often fail to generalize to object category–viewpoint combinations that were not seen during training. The authors investigate the impact of data diversity and architectural choices on the capability of generalizing to out-of-distribution combinations.
Controllers for robotic locomotion patterns deal with complex interactions and need to be carefully designed or extensively trained. Thor and Manoonpong present a modular approach for neural pattern generators that allows incremental and fast learning.